search

nihaomiao / CVPR23_LFDM

The pytorch implementation of our CVPR 2023 paper "Conditional Image-to-Video Generation with Latent Flow Diffusion Models"
BSD 2-Clause "Simplified" License
432 stars 43 forks source link

Can image animation be achieved? like this demo #17

Closed zhanghongyong123456 closed 11 months ago

zhanghongyong123456 commented 11 months ago

like this demo https://twitter.com/pika_labs/status/1678892871670464513

nihaomiao commented 11 months ago

Hi, @zhanghongyong123456, thanks for your interest! Currently, we only train our model with small datasets and only achieve class-conditioned image-to-video (cI2V) generation. To achieve text-conditioned I2V as the link you show, I think more data and computational resources are required to train a text-to-flow diffusion model.